Related Experiment Video
Updated: Aug 2, 2025
Quantitative Structure-Activity Relationship, Activity Prediction, and Molecular Dynamics of Non-nucleotide Reverse Transcriptase Inhibitors
Published on: May 9, 2025
Prediction of KRASG12C inhibitors using conjoint fingerprint and machine learning-based QSAR models
Tarapong Srisongkram1, Patcharapa Khamtang2, Natthida Weerapreeyakul1
1Division of Pharmaceutical Chemistry, Faculty of Pharmaceutical Sciences, Khon Kaen University, 40002, Thailand.
Abstract:
Kirsten rat sarcoma virus G12C (KRASG12C) is the major protein mutation associated with non-small cell lung cancer (NSCLC) severity. Inhibiting KRASG12C is therefore one of the key therapeutic strategies for NSCLC patients. In this paper, a cost-effective data driven drug design employing machine learning-based quantitative structure-activity relationship (QSAR) analysis was built for predicting ligand affinities against KRASG12C protein. A curated and non-redundant dataset of 1033 compounds with KRASG12C inhibitory activity (pIC50) was used to build and test the models. The PubChem fingerprint, Substructure fingerprint, Substructure fingerprint count, and the conjoint fingerprint-a combination of PubChem fingerprint and Substructure fingerprint count-were used to train the models. Using comprehensive validation methods and various machine learning algorithms, the results clearly showed that the XGBoost regression (XGBoost) achieved the highest performance in term of goodness of fit, predictivity, generalizability and model robustness (R2 = 0.81, Q2CV = 0.60, Q2Ext = 0.62, R2 - Q2Ext = 0.19, R2Y-Random = 0.31 ± 0.03, Q2Y-Random = -0.09 ± 0.04). The top 13 molecular fingerprints that correlated with the predicted pIC50 values were SubFPC274 (aromatic atoms), SubFPC307 (number of chiral-centers), PubChemFP37 (≥1 Chlorine), SubFPC18 (Number of alkylarylethers), SubFPC1 (number of primary carbons), SubFPC300 (number of 1,3-tautomerizables), PubChemFP621 (N-C:C:C:N structure), PubChemFP23 (≥1 Fluorine), SubFPC2 (number of secondary carbons), SubFPC295 (number of C-ONS bonds), PubChemFP199 (≥4 6-membered rings), PubChemFP180 (≥1 nitrogen-containing 6-membered ring), and SubFPC180 (number of tertiary amine). These molecular fingerprints were virtualized and validated using molecular docking experiments. In conclusion, this conjoint fingerprint and XGBoost-QSAR model demonstrated to be useful as a high-throughput screening tool for KRASG12C inhibitor identification and drug design.
Insights
Machine learning-based quantitative structure-activity relationship (QSAR) analysis was used to predict KRASG12C inhibitor affinities. The developed XGBoost-QSAR model shows high performance for identifying potential drug candidates for non-small cell lung cancer.
Area of Science:
- Computational Chemistry
- Medicinal Chemistry
- Oncology
Background:
- Kirsten rat sarcoma virus G12C (KRASG12C) is a key mutation driving non-small cell lung cancer (NSCLC) severity.
- Targeting KRASG12C represents a critical therapeutic strategy for NSCLC patients.
Purpose of the Study:
- To develop a cost-effective, data-driven drug design approach using machine learning (ML).
- To build and validate a ML-based quantitative structure-activity relationship (QSAR) model for predicting ligand affinities against the KRASG12C protein.
Main Methods:
- A curated dataset of 1033 compounds with KRASG12C inhibitory activity (pIC50) was utilized.
- Four types of molecular fingerprints (PubChem, Substructure, Substructure count, and conjoint) were employed to train ML models.
- XGBoost regression (XGBoost) was selected as the primary ML algorithm, with comprehensive validation methods applied.
Main Results:
- The XGBoost-QSAR model demonstrated excellent performance, with R2 = 0.81, Q2CV = 0.60, and Q2Ext = 0.62.
- Key molecular fingerprints correlated with pIC50 values included aromatic atoms, chiral centers, chlorine presence, and various ring structures.
- Molecular docking experiments validated the identified molecular fingerprints.
Conclusions:
- The developed conjoint fingerprint and XGBoost-QSAR model is a robust and effective tool.
- This model can be utilized for high-throughput screening to identify novel KRASG12C inhibitors for drug design.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
05:47In Silico Modeling Method for Computational Aquatic Toxicology of Endocrine Disruptors: A Software-Based Approach Using QSAR Toolbox
Published on: August 28, 2019
